MIT and Recursion Release Boltz-2: Next Generation AI Model to Predict Binding Affinity at Unprecedented Speed, Scale, and Accuracy

Rhea-AI Summary

MIT and Recursion (RXRX) have jointly developed and released Boltz-2, a groundbreaking open-source AI model for drug discovery. This biomolecular foundation model can predict both molecular structure and binding affinity simultaneously, approaching the accuracy of industry-standard free energy perturbation (FEP) calculations but at speeds up to 1000x faster. Trained on Recursion's NVIDIA supercomputer BioHive-2, Boltz-2 demonstrates superior performance in the CASP16 affinity challenge and utilizes approximately 5 million binding affinity assay measurements. The model features improved affinity prediction, advanced joint modeling capabilities, and enhanced physical plausibility through Boltz-steering. Released under an MIT license for both academic and commercial use, Boltz-2 represents a significant advancement in making large-scale virtual screening more practical and cost-effective for drug development.

Positive

• Achieves near-FEP accuracy while being 1000x faster and less computationally expensive
• Outperforms all CASP16 affinity challenge participants in predictive power
• Open-source availability under MIT license for both academic and commercial use
• Trained on extensive dataset including 5 million binding affinity assay measurements
• Unique capability to model 3D complex structures while predicting binding affinity and protein dynamics

Negative

• None.

• Boltz-2 is the first biomolecular co-folding model to combine structure and binding affinity prediction, approaching the accuracy of physics-based free energy perturbation (FEP) calculations but at speeds up to 1000x faster in standard benchmarks
• The development of this open source model for academic and commercial use was a collaborative effort, combining MIT’s deep academic expertise with Recursion's AI research and NVIDIA-accelerated supercomputer, BioHive-2

Salt Lake City, UT, June 06, 2025 (GLOBE NEWSWIRE) -- Researchers at the Massachusetts Institute of Technology (MIT) Computer Science and Artificial Intelligence Lab (CSAIL) and Jameel Clinic, alongside TechBio company Recursion (NASDAQ: RXRX), today announced the open-source release of Boltz-2, a first of its kind biomolecular foundation model. Powered by Recursion's NVIDIA supercomputer for its training and validation, this next-generation AI model achieves best-in-class accuracy in jointly modeling complex structures and binding affinities. Boltz-2 represents the next step beyond existing biomolecular structure prediction models like AlphaFold3 and its predecessor, Boltz-1.

“Accurately predicting how strongly molecules bind has been a long-standing challenge in drug discovery—one that required novel machine learning and computer science techniques to address,” said Regina Barzilay, MIT School of Engineering Distinguished Professor for AI and Health, AI faculty lead at Jameel Clinic and CSAIL principal investigator. “Boltz-2 not only addresses this crucial problem but also helps scientists uncover new biological insights and ask questions they couldn't before with standard approaches that are more computationally intensive. Because Boltz-2 is open-source, including its training code, scientists can easily adapt it for specific types of molecules, making it even more powerful as a tool to accelerate discovery."

Specifically, Boltz-2 marks a new era for in silico screening, in standard benchmarks approaching the accuracy of physics-based free energy perturbation (FEP), an industry-standard computational method used to predict the binding affinity of molecules, at speeds up to 1000x faster. The decrease in cost and increase in speed and scale makes large-scale and accurate virtual screening more practical than previously possible, directly addressing a critical bottleneck in small molecule discovery.

"Selecting the right molecules early is one of the most fundamental challenges in drug discovery, with implications for whether R&D programs succeed or fail," said Najat Khan, Chief R&D Officer and Chief Commercial Officer at Recursion. “By predicting both molecular structure and binding affinity simultaneously with unprecedented speed and scale, Boltz-2 gives R&D teams a powerful tool to triage more effectively and focus resources on the most promising compounds. Collaborations like this, bridging academic innovation and industry application, play an important role in advancing the field and, ultimately, improving how we develop and deliver medicines for patients."

Below are key components and differentiators of Boltz-2 vs other methods of predicting biomolecular structures and affinities:

• Improved Affinity Prediction: Near-FEP accuracy on the widely adopted FEP+ benchmark while being over 1,000 times faster and less computationally expensive
• Leading Benchmark Performance: Superior predictive power, demonstrating outperformance over all CASP16 affinity challenge participants 
• Advanced Joint Modeling: Uniquely models 3D complex structures while jointly predicting binding affinity and protein dynamics (e.g., B-factors)
• Controllable & Physically Realistic: Achieves significantly improved physical plausibility using Boltz-steering and offers enhanced user control via template, method, and contact conditioning
• Novel & Expanded Training Data: Trained on molecular dynamics simulations, expanded distillation data, and approximately 5 million binding affinity assay measurements

In line with MIT and Recursion’s commitment to making AI tools accessible for drug developers, Boltz-2 will be open-sourced under an MIT license, making the model, weights, and training pipeline available for both academic and commercial use.

Boltz-2’s development was led by the Boltz team at MIT under the supervision of Professors Regina Barzilay and Tommi Jaakkola alongside a team of researchers from MIT and Recursion. For more information, visit: https://boltz.bio/boltz2.

About Recursion
Recursion (NASDAQ: RXRX) is a clinical stage TechBio company leading the space by decoding biology to radically improve lives. Enabling its mission is the Recursion OS, a platform built across diverse technologies that continuously generate one of the world’s largest proprietary biological and chemical datasets. Recursion leverages sophisticated machine-learning algorithms to distill from its dataset a collection of trillions of searchable relationships across biology and chemistry unconstrained by human bias. By commanding massive experimental scale — up to millions of wet lab experiments weekly — and massive computational scale — owning and operating one of the most powerful supercomputers in the world, Recursion is uniting technology, biology and chemistry to advance the future of medicine.

Recursion is headquartered in Salt Lake City, where it is a founding member of BioHive, the Utah life sciences industry collective. Recursion also has offices in Toronto, Montréal, New York, London, Oxford area, and the San Francisco Bay area. Learn more at www.Recursion.com, or connect on X (formerly Twitter) and LinkedIn.

Investor Contact
Investor@Recursion.com

Media Contact
Media@Recursion.com

FAQ

What is Boltz-2 and how does it improve drug discovery?

Boltz-2 is an AI model that predicts molecular structure and binding affinity simultaneously, operating 1000x faster than traditional methods while maintaining similar accuracy. This speed and accuracy improvement makes virtual screening more practical in drug development.

How does Boltz-2 compare to existing methods like FEP?

Boltz-2 approaches the accuracy of industry-standard free energy perturbation (FEP) calculations while being over 1000 times faster and less computationally expensive.

What are the key features of RXRX's Boltz-2 model?

Key features include improved affinity prediction, superior benchmark performance, advanced joint modeling of 3D structures and binding affinity, enhanced physical plausibility through Boltz-steering, and training on approximately 5 million binding affinity assay measurements.

Who can use Boltz-2 and how is it licensed?

Boltz-2 is open-sourced under an MIT license, making the model, weights, and training pipeline available for both academic and commercial use.

Who developed Boltz-2 and what technology was used?

Boltz-2 was developed collaboratively by MIT's CSAIL and Jameel Clinic researchers alongside Recursion, using Recursion's NVIDIA-powered supercomputer BioHive-2 for training and validation.